| _app | | | 135 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 109 kB | | 0c6c562c |
| async_grpo_trainer.md | 12.5 kB | | e13b1a5d |
| bco_trainer.html | 130 kB | | 4fc488a8 |
| bco_trainer.md | 14.2 kB | | aaea7c8c |
| bema_for_reference_model.html | 90 kB | | 08a5eaca |
| bema_for_reference_model.md | 7.18 kB | | 1474237d |
| callbacks.html | 95.8 kB | | 9657c2e9 |
| callbacks.md | 7.88 kB | | a7d4d734 |
| chat_template_utils.html | 45.5 kB | | 739f807d |
| chat_template_utils.md | 5.3 kB | | 4a9ad5ab |
| clis.html | 53.4 kB | | 742c96ac |
| clis.md | 12.8 kB | | 0f1d0522 |
| community_tutorials.html | 31 kB | | f784ae04 |
| community_tutorials.md | 11 kB | | 86a94c1b |
| cpo_trainer.html | 144 kB | | 9246aea7 |
| cpo_trainer.md | 23 kB | | 35c0454c |
| customization.html | 31 kB | | 5ed71907 |
| customization.md | 4.08 kB | | ed229dad |
| data_utils.html | 62.9 kB | | 86bdd29d |
| data_utils.md | 6.32 kB | | 82bc2276 |
| dataset_formats.html | 223 kB | | 3723f74f |
| dataset_formats.md | 40.2 kB | | 9b0a091f |
| deepspeed_integration.html | 15.8 kB | | 41312e18 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | d19a5e2d |
| distillation_trainer.md | 12.3 kB | | be746ce3 |
| distributing_training.html | 96.5 kB | | 52b3683c |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 2a20ef14 |
| dpo_trainer.md | 30.8 kB | | bc38c39e |
| example_overview.html | 38.3 kB | | 028c77d5 |
| example_overview.md | 16 kB | | 44bce18c |
| experimental_overview.html | 10.8 kB | | 76f0fc53 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 6d7d571f |
| gfpo.md | 5.24 kB | | 1aa55788 |
| gkd_trainer.html | 120 kB | | 2df2139f |
| gkd_trainer.md | 14.3 kB | | 4ea55cff |
| gold_trainer.html | 166 kB | | 31580cb8 |
| gold_trainer.md | 18.1 kB | | 3ce70ebd |
| grpo_trainer.html | 559 kB | | 1736b96f |
| grpo_trainer.md | 55.2 kB | | 525fd3ca |
| grpo_with_replay_buffer.html | 89.6 kB | | 3635529f |
| grpo_with_replay_buffer.md | 6.16 kB | | 075bb5ad |
| gspo_token.html | 50.2 kB | | 34556a8e |
| gspo_token.md | 4.27 kB | | 8888e221 |
| index.html | 29 kB | | ed573f77 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 19f2a9a4 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 8d9ae924 |
| jobs_training.md | 6.44 kB | | 7635e4ba |
| kernels_hub.html | 26.8 kB | | 556ac056 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 142 kB | | c5ed4d40 |
| kto_trainer.md | 18.6 kB | | 91c8bae4 |
| liger_kernel_integration.html | 15 kB | | 1b3f4d3d |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 834 kB | | b621426c |
| llms.txt | 5 kB | | 6ecc0657 |
| lora_without_regret.html | 45 kB | | f8172aa4 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 437c911c |
| merge_model_callback.md | 1.19 kB | | 2d9400fe |
| minillm_trainer.html | 179 kB | | 6492b2bd |
| minillm_trainer.md | 16.4 kB | | f60373de |
| nash_md_trainer.html | 125 kB | | 2258d008 |
| nash_md_trainer.md | 16.4 kB | | 6be80666 |
| nemo_gym.html | 58.5 kB | | 50969926 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | d312de84 |
| online_dpo_trainer.html | 181 kB | | c44474f9 |
| online_dpo_trainer.md | 23.2 kB | | 2e041066 |
| openenv.html | 114 kB | | 65dffe71 |
| openenv.md | 27.8 kB | | 939bd60a |
| orpo_trainer.html | 127 kB | | f740939f |
| orpo_trainer.md | 17.7 kB | | 992f790e |
| paper_index.html | 734 kB | | 0a838d85 |
| paper_index.md | 19.1 kB | | f4caa09f |
| papo_trainer.html | 111 kB | | 1e1abe16 |
| papo_trainer.md | 8.82 kB | | ef6ddb8f |
| peft_integration.html | 131 kB | | b99ad50b |
| peft_integration.md | 23.9 kB | | f2f4ee14 |
| ppo_trainer.html | 278 kB | | ae22004e |
| ppo_trainer.md | 41.4 kB | | 5cf090f4 |
| prm_trainer.html | 117 kB | | 02b5a978 |
| prm_trainer.md | 13.9 kB | | 3dd8c6c4 |
| ptt_integration.html | 29.3 kB | | 95002aae |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 59a1a34c |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | d531a96f |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 1d42ad35 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | ce640b26 |
| reward_trainer.md | 21.5 kB | | 8dee47e4 |
|